US11910228B2ActiveUtilityA1

Method of managing traffic by a user plane function, UPF, corresponding UPF, session management function and network data analytics function

69
Assignee: ERICSSON TELEFON AB L MPriority: Sep 20, 2018Filed: Nov 9, 2018Granted: Feb 20, 2024
Est. expirySep 20, 2038(~12.2 yrs left)· nominal 20-yr term from priority
H04W 28/0268H04L 12/1407H04L 12/1432H04L 41/046H04L 41/052H04L 41/16H04L 43/062H04L 43/08H04L 43/16H04M 15/58H04M 15/66H04W 4/24H04W 4/50H04W 8/18H04W 8/22H04W 24/02H04W 24/08H04W 24/10H04W 28/08H04W 60/00H04W 60/04H04M 2215/2026H04M 2215/7414H04M 2215/7428H04W 84/02H04W 88/16H04W 88/18H04W 92/02H04W 92/24H04M 15/852H04L 41/14H04L 41/0894G06N 3/092
69
PatentIndex Score
1
Cited by
9
References
14
Claims

Abstract

A method of managing traffic associated with a User Equipment, UE, by a User Plane Function, UPF, in a telecommunication network, said UPF being associated with a Session Management Function, SMF, and a Network Data Analytics Function, NWDAF, wherein said UPF has access to an observation space comprising a list of possible states said network may take and wherein said UPF has access to an action space comprising a list of possible actions that said UPF is allowed to perform, said method comprising the steps of receiving a state of said network, wherein said state is comprised by said list of possible states, receiving a reward, wherein said reward indicates a degree of satisfaction of said network to be in said state, receiving network traffic from said UE and performing, triggered by said received traffic, an action comprised by said list of possible actions based on said received state of said network and based on said received reward.

Claims

exact text as granted — not AI-modified
The invention claimed is: 
     
       1. A method of managing traffic associated with a User Equipment (UE) by a User Plane Function (UPF) in a telecommunication network, the UPF associated with a Session Management Function (SMF) and a Network Data Analytics Function (NWDAF), wherein the UPF has access to an observation space comprising a list of possible states the network may take, wherein the UPF has access to an action space comprising a list of possible actions that the UPF is allowed to perform, the method comprising the UPF:
 receiving, from the NWDAF, a state of the network; wherein the state is comprised by the list of possible states; 
 receiving, from the NWDAF, a reward; wherein the reward indicates a degree of satisfaction of the network to be in the state; 
 receiving network traffic from the UE; and 
 performing, in response to receiving the network traffic from the UE, an action comprised by the list of possible actions based on the received state of the network and based on the received reward. 
 
     
     
       2. The method of  claim 1 , further comprising the UPF:
 transmitting, to the NWDAF, a UPF Agent Register Request message to register the UPF in the NWDAF; and 
 receiving, from the NWDAF, a UPF Agent Register Response message acknowledging registration, wherein the UPF Agent Register Response message comprises the observation space. 
 
     
     
       3. The method of  claim 1 , further comprising the UPF:
 receiving, from the SMF, a Session Establishment Request message, wherein the Session Establishment Request message comprises the list of possible actions; wherein the list of possible actions comprises:
 one or more Forwarding Action Rules for indicating forwarding related actions for traffic received from the UE; and/or 
 one or more Quality of Service Enforcement Rules for indicating quality related actions for traffic received from the UE; and 
 
 transmitting, to the SMF, a Session Establishment Response message for acknowledging the Session Establishment Request message. 
 
     
     
       4. The method of  claim 1 , further comprising the UPF:
 transmitting, to the NWDAF, a Network State Report message for requesting the state of the network as well as for a corresponding reward; and 
 receiving, from the NWDAF, the state of the network as well as the corresponding reward. 
 
     
     
       5. The method of  claim 1 , wherein the performing the action comprises the UPF determining which action to perform using a reinforcement learning algorithm taking into account previously performed actions by the UPF associated with previously observed states of the network as well as corresponding rewards. 
     
     
       6. A method of supporting the managing of traffic associated with a User Equipment (UE) by a User Plane Function (UPF) in a telecommunication network, the UPF associated with a Session Management Function (SMF) and a Network Data Analytics Function (NWDAF), wherein the UPF is to have access to an observation space comprising a list of possible states the network may take, the method comprising the NWDAF:
 receiving, from the UPF, a UPF Agent Register Request message to register the UPF in the NWDAF; 
 transmitting, to the UPF, a UPF Agent Register Response message acknowledging the registration, wherein the UPF Agent Register Response message comprises the observation space; 
 determining a state of the network, wherein the state of the network is comprised by the list of possible states; 
 determining a reward, wherein the reward indicates a degree of satisfaction of the network to be in the state; and 
 transmitting, to the UPF, the determined state of the network and the reward. 
 
     
     
       7. The method of  claim 6 , wherein the determining the reward comprises determining the reward based on an overall network load status and/or a Quality of Experience of the UE. 
     
     
       8. A User Plane Function (UPF) configured to manage traffic associated with a User Equipment (UE) in a telecommunication network, the UPF associated with a Session Management Function (SMF) and a Network Data Analytics Function (NWDAF), wherein the UPF has access to an observation space comprising a list of possible states the network may take, wherein the UPF has access to an action space comprising a list of possible actions that the UPF is allowed to perform, the UPF comprising:
 receive circuitry configured to receive:
 a state of the network from the NWDAF, wherein the state is comprised by the list of possible states; 
 a reward from the NWDAF, wherein the reward indicates a degree of satisfaction of the network to be in the state; and 
 network traffic from the UE; and 
 
 processing circuitry configured to perform, in response to receiving the network traffic from the UE, an action comprised by the list of possible actions based on the received state of the network and based on the received reward. 
 
     
     
       9. The UPF of  claim 8 , wherein the UPF is configured to:
 transmit, to the NWDAF, a UPF Agent Register Request message to register the UPF in the NWDAF; and 
 receive, via the receive circuitry and from the NWDAF, a UPF Agent Register Response message acknowledging registration, wherein the UPF Agent Register Response message comprises the observation space. 
 
     
     
       10. The UPF of  claim 8 , wherein the UPF is configured to:
 receive, via the receive circuitry and from the SMF, a Session Establishment Request message, wherein the Session Establishment Request message comprises the list of possible actions, wherein the list of possible actions comprises:
 one or more Forwarding Action Rules for indicating forwarding related actions for traffic received from the UE; and/or 
 one or more Quality of Service Enforcement Rules for indicating quality related actions for traffic received from the UE; and 
 
 transmit, to the SMF, a Session Establishment Response message for acknowledging the Session Establishment Request message. 
 
     
     
       11. The UPF of  claim 8 , wherein the UPF is configured to:
 transmit, to the NWDAF, a Network State Report message for requesting the state of the network as well as for a corresponding reward; and 
 receive, via the receive circuitry and from the NWDAF, the state of the network as well as the corresponding reward. 
 
     
     
       12. The UPF of  claim 8 , wherein the performing the action comprises the UPF determining which action to perform using a reinforcement learning algorithm taking into account previously performed actions by the UPF associated with previously observed states of the network as well as corresponding rewards. 
     
     
       13. A Network Data Analytics Function (NWDAF) configured to support managing of traffic associated with a User Equipment (UE) by a User Plane Function (UPF) in a telecommunication network, the UPF associated with a Session Management Function (SMF) and the Network Data Analytics Function (NWDAF), wherein the UPF is to have access to an observation space comprising a list of possible states the network may take, the NWDAF comprising:
 receive circuitry configured to receive, from the UPF, a UPF Agent Register Request message to register the UPF in the NWDAF; 
 transmit circuitry configured to transmit, to the UPF, a UPF Agent Register Response message acknowledging the registration, wherein the UPF Agent Register Response message comprises the observation space; 
 wherein the NWDAF is configured to:
 determine a state of the network, wherein the state of the network is comprised by the list of possible states; 
 determine a reward, wherein the reward indicates a degree of satisfaction of the network to be in the state; and 
 transmit, to the UPF, the determined state of the network and the reward. 
 
 
     
     
       14. The NWDAF of  claim 13 , wherein the determining the reward comprises determining the reward based on an overall network load status and/or a Quality of Experience of the UE.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.